bunkervm copilot-instructions.md

Project instructions for BunkerVM, a Python library that starts disposable Firecracker microVMs for agents to run untrusted code in hardware-isolated environments. They describe its architecture, conventions, and framework-integration work.

In plain words
What is it for?
Implementing and reviewing BunkerVM changes, including VM lifecycle, isolated code execution, communication between host and guest, and new framework integrations.
Why use it?
They give a coding agent the repository context needed to change the host-side VM manager, guest-side execution service, MCP server, or integrations consistently.

Instructions file for GitHub Copilot

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/ashishgituser/bunkervm/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/ashishgituser/bunkervm

Made for: GitHub Copilot.

Per session 2,299 This file is loaded in full into every session.
When invoked 2,299 The same file — it is already loaded in full.
Security scan B 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.02299 $0.02299
Opus 5 $0.01149 $0.01149
Sonnet 5 $0.00460 $0.00460
Haiku 4.5 $0.00230 $0.00230

Measured yesterday against content hash e1ad73ae6b1c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

bunkervm copilot-instructions.md scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- **vsock** (default): Host ↔ VM via Firecracker UDS. Zero network config, no sudo needed.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- **`tools.py`** — Single `execute(cmd)` function using `subprocess.run()`. The entire OS is the tool — no hardcoded tool list.
.github/copilot-instructions.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BunkerVM — Copilot Instructions

Project Overview

BunkerVM is a Python library (pip install bunkervm) that boots disposable Firecracker microVMs for AI agents to execute untrusted code with hardware-level (KVM) isolation. The core loop: boot VM (~3s) → execute code → destroy VM. Only dependency is mcp.

Architecture

Host side (bunkervm/)                    Guest side (rootfs/bunkervm/)
─────────────────────                    ────────────────────────────
cli.py / __main__.py  →  vm_manager.py  →  [Firecracker process]
                              ↕ vsock                ↕
                       sandbox_client.py  ←→  exec_agent.py (HTTP over vsock)
                              ↑
              mcp_server.py / integrations/
  • vm_manager.py — Firecracker process lifecycle (start/stop/restart), TAP networking setup, rootfs copies. Communicates via vsock UDS (/tmp/bunkervm-vsock.sock).
  • sandbox_client.py — Stdlib-only HTTP client that speaks the Firecracker vsock handshake protocol (CONNECT <port>\nOK <port>\n → HTTP). No external HTTP libs.
  • rootfs/bunkervm/exec_agent.py — Runs inside the VM. Zero-dependency HTTP server (stdlib only, must work on Alpine/musl). Endpoints: /exec, /read-file, /write-file, /list-dir, /health, /status.
  • mcp_server.py — Exposes sandbox operations as MCP tools via FastMCP. Global state set by __main__.py before server starts.
  • integrations/base.pyBunkerVMToolsBase provides 6 shared tool implementations (_run_command, _write_file, _read_file, _list_directory, _upload_file, _download_file). Framework adapters (langchain.py, openai_agents.py, crewai.py) wrap these with framework-specific decorators — never duplicate tool logic in adapters.
  • safety.py — Regex-based command classifier (READ/WRITE/SYSTEM/DESTRUCTIVE/BLOCKED). Defense-in-depth only; the VM is the real isolation boundary.
  • bootstrap.py — Auto-downloads Firecracker bundle to ~/.bunkervm/bundle/ on first run. Falls back to build/ dir in dev mode.
  • config.py — Layered config: CLI args > env vars (BUNKERVM_*) > bunkervm.toml > built-in defaults.

Read the full file on GitHub · 142 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 142 lines · 2,299 tokens per session scan B e1ad73ae6b1c

Subscribe to this mod's changes

bunkervm copilot-instructions.md is an instructions file published in the GitHub repository ashishgituser/bunkervm (0 stars, last pushed 14d ago), licensed MIT. It adds 2,299 tokens to every session, about $0.0115 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

mitos CLAUDE.md

Instructions for mitos-run/mitos, covering claude.md, project overview, operating principles, commands and architecture.

mitos-run/mitos · 2,367 tokens

oring CLAUDE.md

Instructions for hexproofdev/oring, covering claude.md, the discipline, hard constraints and standing rejections.

hexproofdev/oring · 1,181 tokens

arcbox CLAUDE.md

Instructions for arcboxlabs/arcbox, covering repository guidelines for coding agents, project overview, performance targets, platform priority and project structure.

arcboxlabs/arcbox · 3,168 tokens

codex-autoresearch AGENTS.md

Instructions for TheGreenCedar/codex-autoresearch, covering agents.md, purpose and scope, canonical sources, stable product boundaries and source and package boundaries.

TheGreenCedar/codex-autoresearch · 2,034 tokens

autoharness AGENTS.md

Instructions for tigerless-labs/autoharness: This repo uses Open Knowledge — collaborative markdown via MCP. .open-knowledge/config.yml (with optional /.open-knowledge/config.yml; CLI/env may override) is the path contract: content.dir is the root for relative paths; content.include lists globs that add markdown…

tigerless-labs/autoharness · 2,201 tokens

mosoo AGENTS.md

Instructions for langgenius/mosoo, a project described as: The open-source Agent Gallery and Gateway for Codex, Claude Agent SDK, and OpenCode. Developers publish an Agent once behind one HTTP API; users run it in an isolated cloud sandbox—no local harness setup, compute, or runtime infrastructure.

langgenius/mosoo · 115 tokens